π§
Forensics 0.3b Wavlm Oc Softmax Deepfake Classifier model by eliya
β 46.3
π¬Technical Deep Dive
Full Specifications [+]
π Updated daily
Source summary: Based on Hugging Face metadata. Not a recommendation.
π‘οΈ Model Transparency Report
Technical metadata sourced from upstream repositories.
Open Metadata
π Identity & Source
- id
- hf-model--eliya--forensics_0.3b_wavlm_oc_softmax_deepfake_classifier
- slug
- eliya--forensics_0.3b_wavlm_oc_softmax_deepfake_classifier
- source
- huggingface
- author
- eliya
- license
- CC-BY-NC-4.0
- tags
- pytorch, wavlm-aasist-oc-softmax-deepfake-detector, audio-classification, deepfake-detection, anti-spoofing, speech, aasist, wavlm, oc-softmax, multilingual, arxiv:2110.13900, arxiv:2110.01200, arxiv:2010.13995, arxiv:2111.04433, arxiv:2507.21463, base_model:microsoft/wavlm-large, base_model:finetune:microsoft/wavlm-large, license:cc-by-nc-4.0, region:us
βοΈ Technical Specs
- architecture
- DeepfakeDetector
- params billions
- 0.3
- context length
- 4,096
- pipeline tag
- audio-classification
- vram gb
- 1.5
- vram is estimated
- true
- vram formula
- VRAM β (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)
π Engagement & Metrics
- downloads
- 74
Data indexed from public sources. Updated daily.